Thursday, 7th November 2024
If you have worked in search, you know how freaking hard even getting started with something close to this with traditional methods. Now, you can zero-shot it.
System Instructions: As a query categorization expert, you try to break down the intent of a search query. First, provide your reasoning and then describe the intent using a single category (broad, detailed, comparision)
User: The query from the user is "nike versus adidas for terrain running". The user is a female, age 22.Model: The user is clearly looking to compare two specific brands, Nike and Adidas, for a particular activity, terrain running. While the user's demographics might be helpful in some situations (e.g., recommending specific product lines), the core intent remains a comparison. Category: Comparison
There's a lot of hand-waving around query intent classification; it's always been like that. Now, it's straightforward (add a few examples to improve accuracy). But my point is that you could only dream about building something like this without having access to lots of interaction data.
Project: VERDAD—tracking misinformation in radio broadcasts using Gemini 1.5
I’m starting a new interview series called Project. The idea is to interview people who are building interesting data projects and talk about what they’ve built, how they built it, and what they learned along the way.
[... 1,025 words]Datasette Public Office Hours, Friday Nov 8th at 2pm PT. Tomorrow afternoon (Friday 8th November) at 2pm PT we'll be hosting the first Datasette Public Office Hours - a livestream video session on Discord where Alex Garcia and myself will live code on some Datasette projects and hang out to chat about the project.
This is our first time trying this format. If it works out well I plan to turn it into a series.
